为3D高斯点云渲染加入不确定性感知，提升低纹理场景下的定位精度。
VarSplat: Uncertainty-aware 3D Gaussian Splatting for Robust RGB-D SLAM
- 给每个高斯点学习外观方差，显式建模观测可靠性
- 单次光栅化生成可微分的像素级不确定性图，误差降低27%
- 适合需要高鲁棒性的真实世界三维重建与导航任务
基于3D高斯点云的同步定位与建图（SLAM）可实现快速、可微分的渲染和高保真重建。然而，现有3DGS-SLAM方法隐式处理测量可靠性，在低纹理区域、透明表面或复杂反射区域易产生位姿漂移。为此，我们提出VarSplat，一种显式学习每个高斯点外观方差的不确定性感知3DGS-SLAM系统。通过结合阿尔法混合与全方差定律，仅需一次光栅化即可高效生成可微分的像素级不确定性图。该图引导跟踪、子图配准与回环检测聚焦于可靠区域，提升优化稳定性。在Replica（合成数据）及TUM-RGBD、ScanNet、ScanNet++（真实数据）上的实验表明，VarSplat显著提升鲁棒性，在跟踪、建图和新视角合成方面达到或优于现有方法表现。
原文摘要 · Abstract (English)
Simultaneous Localization and Mapping (SLAM) with 3D Gaussian Splatting (3DGS) enables fast, differentiable rendering and high-fidelity reconstruction across diverse real-world scenes. However, existing 3DGS-SLAM approaches handle measurement reliability implicitly, making pose estimation and global alignment susceptible to drift in low-texture regions, transparent surfaces, or areas with complex reflectance properties. To this end, we introduce VarSplat, an uncertainty-aware 3DGS-SLAM system that explicitly learns per-splat appearance variance. By using the law of total variance with alpha compositing, we then render differentiable per-pixel uncertainty map via efficient, single-pass rasterization. This map guides tracking, submap registration, and loop detection toward focusing on reliable regions and contributes to more stable optimization. Experimental results on Replica (synthetic) and TUM-RGBD, ScanNet, and ScanNet++ (real-world) show that VarSplat improves robustness and achieves competitive or superior tracking, mapping, and novel view synthesis rendering compared to existing studies for dense RGB-D SLAM.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。